Argus Phase II

The Space Development Agency (SDA) is developing the Proliferated Warfighter Space Architecture (PWSA, formerly the National Defense Space Architecture), which entails a national defense mission to provide constant global surveillance for military threats. However, picking targets out of a noisy, changing, and varied background and tracking them requires advanced algorithms and system designs combined with extensive testing. In Phase I, Stellar Science developed Argus, a robust modeling and simulation framework for evaluating satellite-based detection and tracking. Argus is built on top of the Advanced Framework for Simulation, Integration, and Modeling (AFSIM), the trusted DoD simulation framework, and leverages a radiometrically accurate ray-tracing scene generation tool that includes realistically modeled terrain backgrounds. Argus’ plug-in infrastructure allows many algorithms to be tested, even if developed by others. We also developed an advanced detection and tracking algorithm based on an infrared-path image (IPI) model that has achieved state-of-the-art performance in target identification. By developing these in a way appropriate for an open system architecture, they will be readily available for transition to a real-world system. In Phase II, we will improve the Argus framework and validation scenarios, and test the detection and tracking algorithms against real satellite imagery. Argus will be improved to allow user-supplied images to be used for detection and tracking, including by adding synthetic targets to these images. It will be integrated with a distributed tracking framework to allow testing of whole-constellation performance. We will also add cloud modeling, improve our target modeling, and add realistic sensor parameters to increase image realism, along with a number of other improvements. After improving the framework and scenarios, we will perform verification and validation of our detection and tracking algorithms using both synthetic and government-supplied imagery. Using these scenarios, we will also explore the hyperparameter space to optimize algorithm performance, while also considering size, weight, and power tradeoffs for algorithm and sensor performance. Stellar Science is a software development company specializing in advanced algorithm development, with deep experience in space domain modeling and simulation, radiometrically accurate image simulation, image processing, computer vision, and more. Phase II improvements to Argus will combine this expertise to meet and exceed SDA’s requirements for testing proliferated satellite architectures. Its flexibility and robustness will enable it to fulfill program needs for Phase II and beyond.